Loss-sensitive Training of Probabilistic Conditional Random Fields

Details Loss-sensitive Training of Probabilistic Conditional Random Fields Loss-sensitive Training of Probabilistic Conditional Random Fields

2011-07-09

arxiv.org/abs/1107.1805v1

Statistics

Machine Learning

Scientific paper

We consider the problem of training probabilistic conditional random fields (CRFs) in the context of a task where performance is measured using a specific loss function. While maximum likelihood is the most common approach to training CRFs, it ignores the inherent structure of the task's loss function. We describe alternatives to maximum likelihood which take that loss into account. These include a novel adaptation of a loss upper bound from the structured SVMs literature to the CRF context, as well as a new loss-inspired KL divergence objective which relies on the probabilistic nature of CRFs. These loss-sensitive objectives are compared to maximum likelihood using ranking as a benchmark task. This comparison confirms the importance of incorporating loss information in the probabilistic training of CRFs, with the loss-inspired KL outperforming all other objectives.

Affiliated with

Also associated with

No associations

Rating

Loss-sensitive Training of Probabilistic Conditional Random Fields does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Loss-sensitive Training of Probabilistic Conditional Random Fields, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Loss-sensitive Training of Probabilistic Conditional Random Fields will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-675285